neural net
Latest
British researchers design a million-chip neural network 1/100 as complex as your brain
If you want some idea of the complexity of the human brain, consider this: a group of British universities plans to link as many as a million ARM processors in order to simulate just a small fraction of it. The resulting model, called SpiNNaker (Spiking Neural Network architecture), will represent less than one percent of a human's gray matter, which contains 100 billion neurons. (Take that, mice brains!) Yet even this small scale representation, researchers believe, will yield insight into how the brain functions, perhaps enabling new treatments for cognitive disorders, similar to previous models that increased our understanding of schizophrenia. As these neural networks increase in complexity, they come closer to mimicking human brains -- perhaps even developing the ability to make their own Skynet references.
Schizophrenic computer may help us understand similarly afflicted humans
Although we usually prefer our computers to be perfect, logical, and psychologically fit, sometimes there's more to be learned from a schizophrenic one. A University of Texas experiment has doomed a computer with dementia praecox, saddling the silicon soul with symptoms that normally only afflict humans. By telling the machine's neural network to treat everything it learned as extremely important, the team hopes to aid clinical research in understanding the schizophrenic brain -- following a popular theory that suggests afflicted patients lose the ability to forget or ignore frivolous information, causing them to make illogical connections and paranoid jumps in reason. Sure enough, the machine lost it, and started spinning wild, delusional stories, eventually claiming responsibility for a terrorist attack. Yikes. We aren't hastening the robot apocalypse if we're programming machines to go mad intentionally, right?
Researchers solve the "Cocktail Party Problem"
We suppose it depends on your level of paranoia whether you view the inability of government computers to listen to recordings of confusing party conversation muddle and pick out individual voices for special scrutiny a "Problem." But however your personal opinion on the matter falls, some researchers are claiming to have finally solved the "Cocktail Party Problem," which has befuddled scientists and snoops throughout the ages. The basic gist of the idea is that while a human can easily stand in the midst of a myriad of conversations and identify and follow each speaker individually, automated computer processing couldn't replicate this ability until now without having as many microphones as there were sound sources. Now a pair of University of Missouri-Columbia students are claiming victory over the problem using the "neural net" technique. In much the same way a human has natural abilities and responses to situations without exactly knowing why or how, the computer is trained through repetitive exposure to inputs (muddled sound) and outputs (single sources) until the computer figures out its own method for distinguishing -- though the actual process is still a tad mysterious. Of course, with the NSA involved and partially funding the project, they probably wouldn't have it any other way.
